Modeling hourly dissolved oxygen concentration (DO) using two different adaptive neuro-fuzzy inference systems (ANFIS): a comparative study

This article presents a comparison of two adaptive neuro-fuzzy inference systems (ANFIS)-based neuro-fuzzy models applied for modeling dissolved oxygen (DO) concentration. The two models are developed using experimental data collected from the bottom (USGS station no: 420615121533601) and top (USGS station no: 420615121533600) stations at Klamath River at site KRS12a nr Rock Quarry, Oregon, USA. The input variables used for the ANFIS models are water pH, temperature, specific conductance, and sensor depth. Two ANFIS-based neuro-fuzzy systems are presented. The two neuro-fuzzy systems are: (1) grid partition-based fuzzy inference system, named ANFIS_GRID, and (2) subtractive-clustering-based fuzzy inference system, named ANFIS_SUB. In both models, 60 % of the data set was randomly assigned to the training set, 20 % to the validation set, and 20 % to the test set. The ANFIS results are compared with multiple linear regression models. The system proposed in this paper shows a novelty approach with regard to the usage of ANFIS models for DO concentration modeling.

[1]  Xiaoou Li,et al.  Online fuzzy modeling with structure and parameter learning , 2009, Expert Syst. Appl..

[2]  William D Taylor,et al.  Using stable isotopes of dissolved oxygen for the determination of gas exchange in the Grand River, Ontario, Canada. , 2013, Water research.

[3]  H. Stefan,et al.  Dissolved oxygen model for regional lake analysis , 1994 .

[4]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

[5]  Stewart A. Rounds,et al.  Dissolved oxygen analysis, TMDL model comparison, and particulate matter shunting—Preliminary results from three model scenarios for the Klamath River upstream of Keno Dam, Oregon , 2012 .

[6]  C. Singaraja,et al.  A Study on the Behavior of the Dissolved Oxygen in the Shallow Coastal Wells of Cuddalore District, Tamilnadu, India , 2012, Water Quality, Exposure and Health.

[7]  Stewart A. Rounds,et al.  Review of revised Klamath River Total Maximum Daily Load models from Link River Dam to Keno Dam, Oregon , 2013 .

[8]  Qingzhong Liu,et al.  Predicting injection profiles using ANFIS , 2007, Inf. Sci..

[9]  J. Berlamont,et al.  Modelling of dissolved oxygen and biochemical oxygen demand in river water using a detailed and a simplified model , 2003 .

[10]  Philippe Benoit,et al.  Modeling of dissolved oxygen levels in the bottom waters of the Lower St. Lawrence Estuary: Coupling of benthic and pelagic processes , 2006 .

[11]  A. K. Misra,et al.  Modeling the depletion of dissolved oxygen due to algal bloom in a lake by taking Holling type-III interaction , 2011, Appl. Math. Comput..

[12]  Stefano Marsili-Libelli,et al.  Spatio-temporal dissolved oxygen dynamics in the Orbetello lagoon by fuzzy pattern recognition , 2009 .

[13]  R. Yager,et al.  Approximate Clustering Via the Mountain Method , 1994, IEEE Trans. Syst. Man Cybern. Syst..

[14]  Vincent Hull,et al.  Modelling dissolved oxygen dynamics in coastal lagoons , 2008 .

[15]  S. Heddam,et al.  ANFIS-based modelling for coagulant dosage in drinking water treatment plant: a case study , 2012, Environmental Monitoring and Assessment.

[16]  Jasna Radulović,et al.  Neural network modeling of dissolved oxygen in the Gruža reservoir, Serbia , 2010 .

[17]  S. Shrestha,et al.  Modelling eutrophication and microbial risks in peri-urban river systems using discriminant function analysis. , 2012, Water research.

[18]  Marc L Serre,et al.  Using river distances in the space/time estimation of dissolved oxygen along two impaired river networks in New Jersey. , 2009, Water research.

[19]  Nikita Basant,et al.  Linear and nonlinear modeling for simultaneous prediction of dissolved oxygen and biochemical oxygen demand of the surface water — A case study , 2010 .

[20]  D. Papamichail,et al.  Cascade Correlation Artificial Neural Networks for Estimating Missing Monthly Values of Water Quality Parameters in Rivers , 2007 .

[21]  K. P. Sudheer,et al.  Short‐term flood forecasting with a neurofuzzy model , 2005 .

[22]  Hisao Ishibuchi,et al.  Performance evaluation of fuzzy classifier systems for multidimensional pattern classification problems , 1999, IEEE Trans. Syst. Man Cybern. Part B.

[23]  Mahdi Eftekhari,et al.  Extracting compact fuzzy rules for nonlinear system modeling using subtractive clustering, GA and unscented filter , 2008 .

[24]  N. K. Goel,et al.  Takagi–Sugeno fuzzy inference system for modeling stage–discharge relationship , 2006 .

[25]  S. Chiu.  Method and software for extracting fuzzy classification rules by subtractive clustering , 1996, Proceedings of North American Fuzzy Information Processing.

[26]  Li Li,et al.  Evaluation of dissolved oxygen in water by artificial neural network and sample optimization , 2008 .

[27]  Sudipto Mandal,et al.  Dynamic modelling of dissolved oxygen in the creeks of Sagar island, Hooghly–Matla estuarine system, West Bengal, India , 2012 .

[28]  Dingjiang Chen,et al.  Artificial neural network modelling of concentrations of nitrogen, phosphorus and dissolved oxygen in a non‐point source polluted river in Zhejiang Province, southeast China , 2009 .

[29]  Richard J. Williams,et al.  Modelling in-stream temperature and dissolved oxygen at sub-daily time steps: an application to the River Kennet, UK. , 2012, The Science of the total environment.

[30]  Peeyush Chandra,et al.  Modeling the depletion of dissolved oxygen in a lake due to algal bloom: Effect of time delay , 2011 .

[31]  Sven Erik Jørgensen,et al.  Modelling diurnal variation of dissolved oxygen in waste stabilization ponds , 2000 .

[32]  Daoliang Li,et al.  Prediction of Dissolved Oxygen Content in Aquaculture of Hyriopsis Cumingii Using Elman Neural Network , 2011, CCTA.

[33]  Floris Linnebank,et al.  The river Mesta case study: A qualitative model of dissolved oxygen in aquatic ecosystems , 2009, Ecol. Informatics.

[34]  Kwok-wing Chau,et al.  A review on integration of artificial intelligence into water quality modelling. , 2006, Marine pollution bulletin.

[35]  Roberto Revelli,et al.  Stochastic modelling of DO and BOD components in a stream with random inputs , 2006 .

[36]  A. Vicino,et al.  Nonlinear time series analysis of dissolved oxygen in the Orbetello Lagoon (Italy) , 2007 .

[37]  Tong Yu,et al.  Model development for prediction and mitigation of dissolved oxygen sags in the Athabasca River, Canada. , 2013, The Science of the total environment.

[38]  Stephen L. Chiu,et al.  Fuzzy Model Identification Based on Cluster Estimation , 1994, J. Intell. Fuzzy Syst..